In this video, we will learn about RNN and its different types of architecture which are used for different types of applications.

In CNN we are able to extract features from images using convolution operations but it is not able to memorize the data or the information regarding the sequence that is there in a dataset. Due to this lack of functionality RNN comes into the picture.

Different types of RNN architecture are:
1) One-to-One
2) Many-to-One
3) One-to-Many
4) Many-to-Many

Each type of architecture is used for different types of applications like Speech Recognition, Language Modelling, Name entity recognition, Music generation and many others as well. To improve these architectures slightly complex intermediate units like LSTM, and GRUs are used to build NLP models for real-world applications.

Types of RNN:
https://www.geeksforgeeks.org/types-of-recurrent-neural-networks-rnn-in-tensorflow/

Introduction to RNN:
https://www.geeksforgeeks.org/introduction-to-recurrent-neural-network/